<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Hallucination on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/hallucination/</link><description>Recent content in Hallucination on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Tue, 30 Jun 2026 09:20:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/hallucination/index.xml" rel="self" type="application/rss+xml"/><item><title>大模型幻觉问题：根因分析与缓解技术全景</title><link>https://guijiagi.com/posts/llm-hallucination-mitigation/</link><pubDate>Tue, 30 Jun 2026 09:20:00 +0800</pubDate><guid>https://guijiagi.com/posts/llm-hallucination-mitigation/</guid><description>深入分析大模型幻觉问题的根因，系统介绍从训练到推理全链路的缓解技术</description></item><item><title>大模型幻觉问题 2026：根因分析与缓解策略</title><link>https://guijiagi.com/posts/llm-hallucination-2026-analysis/</link><pubDate>Sun, 28 Jun 2026 11:10:00 +0800</pubDate><guid>https://guijiagi.com/posts/llm-hallucination-2026-analysis/</guid><description>LLM幻觉问题的深度根因分析与2026年最新缓解策略：从RAG到自验证的完整方案</description></item></channel></rss>